Cardiff School of Engineering

Laboratory A – Uncertainty Analysis Cover Sheet.

Module Details
Module Name: Mechanical Engineering Labs Module No: EN2024.

Laboratory Title: Uncertainty Analysis

Lecturer running the Laboratory: Prof. R Marsh

Personal Details

Name: Henry Betts Student No: C22039406

Personal Tutor: Dr. Z Wu Degree: Mechanical / Medical Eng

(circle the appropriate degree)

Declaration
I hereby declare that, except where I have made clear and full reference to the
work of others, this submission, and all the material (e.g. text, pictures, diagrams)
contained in it, is my own work, has not previously been submitted for
assessment, and I have not knowingly allowed it to be copied by another student.
In the case of group projects, the contribution of group members has been
appropriately quantified.
I understand that deceiving, or attempting to deceive, examiners by passing off
the work of another as my own is plagiarism. I also understand that plagiarising
another's work, or knowingly allowing another student to plagiarise from my work,
is against University Regulations and that doing so will result in loss of marks and
disciplinary proceedings. I understand and agree that the University’s plagiarism
software ‘Turnitin’ may be used to check the originality of the submitted
coursework.

Signed: …..…………………………………….………... Date: 15/02/2024

EN2024 Mechanical Engineering Labs Henry Betts

Uncertainty Analysis

Henry Betts
Student No.: 22039406

15th February 2024

Abstract

This report presents an uncertainty analysis of temperature measurements using

thermocouples in a climate-controlled manufacturing process. The analysis includes
calculations of mean, standard deviation, residual plot, and Chi-Square normality test to
assess the repeatability and reliability of the temperature measurements.

2
EN2024 Mechanical Engineering Labs Henry Betts

Table of contents

Section Page Number

1 Introduction

2 Methodology

3 Results

4 Discussion

5 Conclusion

6 Appendices

7 References

3
EN2024 Mechanical Engineering Labs Henry Betts

1. Introduction

Thermocouples are widely used for temperature measurement due to their simplicity and
reliability. However, understanding the uncertainty associated with temperature
measurements is crucial for ensuring the accuracy and reliability of the data obtained.

2. Methodology

2.1 Data Collection

The temperature measurements were collected from the climate-controlled manufacturing
process under nominally stable operating conditions.
The dataset was generated using the method provided on Learning Central.
2.2 Analysis
Mean Calculation: Average temperature measurement.
Standard Deviation: Measure of the dispersion of temperature measurements.
Residuals Plot: Visualization of the scatter around the average temperature.
Chi-Square Test of Normality: Assessing if the data follows a normal distribution.
2.3 Excel Formulas Used
Mean: =AVERAGE(data)
Standard Deviation: =STDEV(data)
Residuals Calculation: =data - mean
Chi-Square Test: Utilized Excel's built-in functions or statistical packages.

3. Results

3.1 Mean Temperature

The average temperature measurement: [Insert Mean Value] °C
3.2 Standard Deviation
Standard deviation of temperature measurements: [Insert Standard Deviation] °C
3.3 Residuals Plot
[Insert Residuals Plot Image]
3.4 Chi-Square Test of Normality
Chi-Square Test Statistic: [Insert Chi-Square Test Statistic]
Degrees of Freedom: [Insert Degrees of Freedom]
p-value: [Insert p-value]

4
EN2024 Mechanical Engineering Labs Henry Betts

4. Discussion

4.1 Confidence Level of Repeatability

The confidence level of repeatability is determined by the standard deviation and the desired
level of confidence (e.g., 95%).
4.2 Data Selection for Testing
The data selection process involved collecting temperature measurements under stable
operating conditions to ensure consistency and repeatability.
4.3 Degrees of Freedom
The degrees of freedom were calculated based on the number of data points and the number
of parameters estimated in the analysis.
4.4 Recommendation
Based on the analysis, if this were a real test, it would be recommended to further investigate
any deviations from normality and assess the impact on measurement uncertainty.
Additionally, continuous monitoring and calibration of thermocouple systems are advised to
ensure accurate temperature measurements.

5. Conclusion

The uncertainty analysis conducted on the thermocouple temperature measurements

provides insights into the repeatability and reliability of the data. Further investigation into
deviations from normality and regular calibration of the measurement system are
recommended to improve accuracy and confidence in temperature measurements.

6. Appendices

Appendix A: Excel Sheets (with formulas)

Appendix B: Residuals Plot
Appendix C: Chi-Square Test Results